Terms:
SAE International Journal of Passenger Cars Electronic and Electrical Systems
AND
11
AND
1
Show Only

Collections

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

2-D CFAR Procedure of Multiple Target Detection for Automotive Radar

SAE International Journal of Passenger Cars - Electronic and Electrical Systems

Automotive Sensors Group-Libo Huang
Tongji University-Sen Li, Xin Bi, Bin Tan
  • Journal Article
  • 07-11-01-0007
Published 2017-09-23 by SAE International in United States
In Advanced Driver Assistant System (ADAS), the automotive radar is used to detect targets or obstacles around the vehicle. The procedure of Constant False Alarm Rate (CFAR) plays an important role in adaptive targets detection in noise or clutter environment. But in practical applications, the noise or clutter power is absolutely unknown and varies over the change of range, time and angle. The well-known cell averaging (CA) CFAR detector has a good detection performance in homogeneous environment but suffers from masking effect in multi-target environment. The ordered statistic (OS) CFAR is more robust in multi-target environment but needs a high computation power. Therefore, in this paper, a new two-dimension CFAR procedure based on a combination of Generalized Order Statistic (GOS) and CA CFAR named GOS-CA CFAR is proposed. Besides, the Linear Frequency Modulation Continuous Wave (LFMCW) radar simulation system is built to produce a series of rapid chirp signals. Then the echo signals are converted into a two-dimensional Range-Doppler matrix (RDM), which contains information about the targets as well as background clutter and noise, through…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

3D Scene Reconstruction with Sparse LiDAR Data and Monocular Image in Single Frame

SAE International Journal of Passenger Cars - Electronic and Electrical Systems

Tsinghua University-Yuanxin Zhong, Sijia Wang, Shichao Xie, Zhong Cao, Kun Jiang, Diange Yang
  • Journal Article
  • 07-11-01-0005
Published 2017-09-23 by SAE International in United States
Real-time reconstruction of 3D environment attributed with semantic information is significant for a variety of applications, such as obstacle detection, traffic scene comprehension and autonomous navigation. The current approaches to achieve it are mainly using stereo vision, Structure from Motion (SfM) or mobile LiDAR sensors. Each of these approaches has its own limitation, stereo vision has high computational cost, SfM needs accurate calibration between a sequences of images, and the onboard LiDAR sensor can only provide sparse points without color information. This paper describes a novel method for traffic scene semantic segmentation by combining sparse LiDAR point cloud (e.g. from Velodyne scans), with monocular color image. The key novelty of the method is the semantic coupling of stereoscopic point cloud with color lattice from camera image labelled through a Convolutional Neural Network (CNN). The presented method comprises three main process: (I) perform semantic segmentation on color image from monocular camera by using CNN, (II) extract ideal surfaces and other structural information from point cloud, (III) improve the image segmentation with the extracts and label the…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Obstacle Avoidance for Self-Driving Vehicle with Reinforcement Learning

SAE International Journal of Passenger Cars - Electronic and Electrical Systems

Beihang University-Xiaopeng Zong, Guoyan Xu, Guizhen Yu, Hongjie Su, Chaowei Hu
  • Journal Article
  • 07-11-01-0003
Published 2017-09-23 by SAE International in United States
Obstacle avoidance is an important function in self-driving vehicle control. When the vehicle move from any arbitrary start positions to any target positions in environment, a proper path must avoid both static obstacles and moving obstacles of arbitrary shape. There are many possible scenarios, manually tackling all possible cases will likely yield a too simplistic policy. In this paper reinforcement learning is applied to the problem to form effective strategies. There are two major challenges that make self-driving vehicle different from other robotic tasks. Firstly, in order to control the vehicle precisely, the action space must be continuous which can’t be dealt with by traditional Q-learning. Secondly, self-driving vehicle must satisfy various constraints including vehicle dynamics constraints and traffic rules constraints. Three contributions are made in this paper. Firstly, an improved Deep Deterministic Policy Gradients (DDPG) algorithm is proposed to solve the problem of continuous action space, so that the continuous steering angle and acceleration can be obtained. Secondly, according to the vehicle constraints include inside and outside, a more reasonable path for obstacle avoidance…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Integrated Positioning Method for Intelligent Vehicle Based on GPS and UWB

SAE International Journal of Passenger Cars - Electronic and Electrical Systems

Jilin University-Min Ke, Bing Zhu, Jian Zhao, Weiwen Deng
  • Journal Article
  • 07-11-01-0004
Published 2017-09-23 by SAE International in United States
Knowledge of intelligent vehicle absolute position is a vital premise for the implementation of decision programming, kinematic and dynamics control. In order to achieve high accuracy positioning and reduce running cost as much as possible under all operating conditions, this paper proposed an integrated positioning method based on GPS and Ultra Wide Band(UWB) for intelligent vehicle’s navigation and position system. In this method, GPS and UWB are alternately active according to the confidence level of GPS signal. When the vehicle is traveling in a wide-open area and GPS signal is well received, the positioning results of Dead Reckoning system are corrected by the low frequency positioning output from GPS. During the correcting process, in order to realize the better fusion of measurement data, a simplified federal Kalman filter was designed by using indirect method. When the vehicle is in places where GPS signal can hardly be received such as tunnel, the positioning results based on UWB positioning technology can be adopted to substitute the lost GPS signal for vehicle integrated positioning. The algorithm used in…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

HMI for Left Turn Assist (LTA)

SAE International Journal of Passenger Cars - Electronic and Electrical Systems

Adam Opel GmbH-Lena Rittger
ESG Elektroniksystem- und Logistik-GmbH-Henning Kienast
  • Journal Article
  • 07-11-01-0002
Published 2018-03-01 by SAE International in United States
Potential collisions with oncoming traffic while turning left belong to the most safety-critical situations accounting for ~25% of all intersection crossing path crashes. A Left Turn Assist (LTA) was developed to reduce the number of crashes. Crucial for the effectiveness of the system is the design of the human-machine interface (HMI), i.e. defining how the system uses the calculated crash probability in the communication with the driver. A driving simulator study was conducted evaluating a warning strategy for two use cases: firstly, the driver comes to a stop before turning (STOP), and secondly, the driver moves on without stopping (MOVE). Forty drivers drove through three STOP and two MOVE scenarios. For the STOP scenarios, the study compared the effectiveness of an audio-visual warning with an additional brake intervention and a baseline. For the MOVE scenarios, the study analyzed the effectiveness of the audio-visual warning against a baseline. The results showed that the brake intervention is highly effective resulting in significantly larger minimal distances between the two vehicles. For the MOVE scenarios, the warning strategy is…
This content contains downloadable datasets
Annotation ability available

Analysis of Evaporative and Exhaust-Related On-Board Diagnostic (OBD) Readiness Monitors and DTCs Using I/M and Roadside Data

SAE International Journal of Passenger Cars - Electronic and Electrical Systems

Eastern Research Group, Inc.-Michael Sabisch, Meredith Weatherby, Sandeep Kishan
U.S. Environmental Protection Agency-Carl Fulper
  • Journal Article
  • 07-11-01-0001
Published 2018-03-01 by SAE International in United States
Under contract to the EPA, Eastern Research Group analyzed light-duty vehicle OBD monitor readiness and diagnostic trouble codes (DTCs) using inspection and maintenance (I/M) data from four states. Results from roadside pullover emissions and OBD tests were also compared with same-vehicle I/M OBD results from one of the states. Analysis focused on the evaporative emissions control (evap) system, the catalytic converter (catalyst), the exhaust gas recirculation (EGR) system and the oxygen sensor and oxygen sensor heater (O2 system). Evap and catalyst monitors had similar overall readiness rates (90% to 95%), while the EGR and O2 systems had higher readiness rates (95% to 98%). Approximately 0.7% to 2.5% of inspection cycles with a “ready” evap monitor had at least one stored evap DTC, but DTC rates were under 1% for the catalyst and EGR systems, and under 1.1% for the O2 system, in the states with enforced OBD programs. Monitor readiness decreased, and DTC rates increased, as vehicles aged. DTCs were typically limited to a small subset of all possible DTCs for any particular system. For…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Efficient Lane Detection Using Deep Lane Feature Extraction Method

SAE International Journal of Passenger Cars - Electronic and Electrical Systems

Beihang University-Guizhen Yu, Zhangyu Wang, Xinkai Wu, Yalong Ma, Yunpeng Wang
  • Journal Article
  • 07-11-01-0006
Published 2017-09-23 by SAE International in United States
In this paper, an efficient lane detection using deep feature extraction method is proposed to achieve real-time lane detection in diverse road environment. The method contains three main stages: 1) pre-processing, 2) deep lane feature extraction and 3) lane fitting. In pre-processing stage, the inverse perspective mapping (IPM) is used to obtain a bird's eye view of the road image, and then an edge image is generated using the canny operator. In deep lane feature extraction stage, an advanced lane extraction method is proposed. Firstly, line segment detector (LSD) is applied to achieve the fast line segment detection in the IPM image. After that, a proposed adaptive lane clustering algorithm is employed to gather the adjacent line segments generated by the LSD method. Finally, a proposed local gray value maximum cascaded spatial correlation filter (GMSF) algorithm is used to extract the target lane lines among the multiple lines. In lane fitting stage, Kalman filtering is used to improve the accuracy of extraction result, which is followed by RANSAC algorithm, who is applied to fit the…
This content contains downloadable datasets
Annotation ability available